add whisperx support

meetus/transcript_merger.py

@@ -70,8 +70,10 @@ class TranscriptMerger:
                     for seg in data
                 ]
 
-            # Group by interval if requested
-            if group_interval and segments:
+            # Group by interval if requested, but skip if we have speaker diarization
+            # (merge_transcripts will group by speaker instead)
+            has_speakers = any(seg.get('speaker') for seg in segments)
+            if group_interval and segments and not has_speakers:
                 segments = self.group_audio_by_intervals(segments, group_interval)
 
             return segments
@@ -164,13 +166,14 @@ class TranscriptMerger:
     ) -> List[Dict]:
         """
         Merge audio and screen transcripts by timestamp.
+        Groups consecutive audio from same speaker until a screen frame interrupts.
 
         Args:
             audio_segments: List of audio transcript segments
             screen_segments: List of screen OCR segments
 
         Returns:
-            Merged list sorted by timestamp
+            Merged list sorted by timestamp, with audio grouped by speaker
         """
         # Mark segment types
         for seg in audio_segments:
@@ -182,7 +185,46 @@ class TranscriptMerger:
         all_segments = audio_segments + screen_segments
         all_segments.sort(key=lambda x: x['timestamp'])
 
-        return all_segments
+        # Group consecutive audio segments by speaker (screen frames break groups)
+        grouped = []
+        current_group = None
+
+        for seg in all_segments:
+            if seg['type'] == 'screen':
+                # Screen frame: flush current group and add frame
+                if current_group:
+                    grouped.append(current_group)
+                    current_group = None
+                grouped.append(seg)
+            else:
+                # Audio segment
+                speaker = seg.get('speaker')
+                if current_group is None:
+                    # Start new group
+                    current_group = {
+                        'timestamp': seg['timestamp'],
+                        'text': seg['text'],
+                        'speaker': speaker,
+                        'type': 'audio'
+                    }
+                elif speaker == current_group.get('speaker'):
+                    # Same speaker, append text
+                    current_group['text'] += ' ' + seg['text']
+                else:
+                    # Speaker changed, flush and start new group
+                    grouped.append(current_group)
+                    current_group = {
+                        'timestamp': seg['timestamp'],
+                        'text': seg['text'],
+                        'speaker': speaker,
+                        'type': 'audio'
+                    }
+
+        # Don't forget last group
+        if current_group:
+            grouped.append(current_group)
+
+        return grouped
 
     def format_for_claude(
         self,